{"type":"ScholarlyArticle","title":"TiRGN: Time-Guided Recurrent Graph Network with Local-Global Historical Patterns for Temporal Knowledge Graph Reasoning","authors":[{"name":"Yujia Li","slug":"yujia-li","given":"Yujia","family":"Li","affiliation":"School of Computer Science of Technology , East China Normal University , Shanghai 200062 , China"},{"name":"Shiliang Sun","slug":"shiliang-sun","given":"Shiliang","family":"Sun","affiliation":"School of Computer Science of Technology , East China Normal University , Shanghai 200062 , China"},{"name":"Jing Zhao","slug":"jing-zhao","given":"Jing","family":"Zhao","affiliation":"School of Computer Science of Technology , East China Normal University , Shanghai 200062 , China"}],"abstract":"Temporal knowledge graphs (TKGs) have been widely used in various fields that model the dynamics of facts along the timeline. In the extrapolation setting of TKG reasoning, since facts happening in the future are entirely unknowable, insight into history is the key to predicting future facts. However, it is still a great challenge for existing models as they hardly learn the characteristics of historical events adequately. From the perspective of historical development laws, comprehensively considering the sequential, repetitive, and cyclical patterns of historical facts is conducive to predicting future facts. To this end, we propose a novel representation learning model for TKG reasoning, namely TiRGN, a time-guided recurrent graph network with local-global historical patterns. Specifically, TiRGN uses a local recurrent graph encoder network to model the historical dependency of events at adjacent timestamps and uses the global history encoder network to collect repeated historical facts. After the trade-off between the two encoders, the final inference is performed by a decoder with periodicity. We use six benchmark datasets to evaluate the proposed method. The experimental results show that TiRGN outperforms the state-of-the-art TKG reasoning methods in most cases.","doi":"10.24963/ijcai.2022/299","url":"https://ijcai.org/proceedings/2022/299","pdf":"https://ijcai.org/proceedings/2022/0299.pdf","markdown":"https://ijcai.org/proceedings/2022/299.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/299","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Data Mining","track":"Main Track","number":299,"pages":{"first":2152,"last":2158},"keywords":["Knowledge Representation and Reasoning: Qualitative, Geometric, Spatial, Temporal Reasoning","Data Mining: Knowledge Graphs and Knowledge Base Completion"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986841","length_sec":90,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984984","length_sec":343,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Bordes et al., 2013] Antoine Bordes, Nicolas Usunier, Alberto García-Durán, Jason Weston, and Oksana Yakhnenko. Translating embeddings for modeling multi-relational data. In NeurIPS, pages 2787-2795, 2013.","title":"Translating embeddings for modeling multi-relational data","authors":"Antoine Bordes, Nicolas Usunier, Alberto García-Durán, Jason Weston, Oksana Yakhnenko","year":"2013","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Deng et al., 2020] Songgaojun Deng, Huzefa Rangwala, and Yue Ning. Dynamic knowledge graph based multi- event forecasting. In KDD, pages 1585-1595, 2020.","title":"Dynamic knowledge graph based multievent forecasting","authors":"Deng","year":"2020","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[García-Durán et al., 2018] Alberto García-Durán, Sebasti- jan Dumancic, and Mathias Niepert. Learning sequence encoders for temporal knowledge graph completion. In EMNLP, pages 4816-4821, 2018.","title":"Learning sequence encoders for temporal knowledge graph completion","authors":"Alberto García-Durán, Sebastijan Dumancic, Mathias Niepert","year":"2018","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Goel et al., 2020] Rishab Goel, Seyed Mehran Kazemi, Marcus Brubaker, and Pascal Poupart. Diachronic embed- ding for temporal knowledge graph completion. In AAAI, pages 3988-3995, 2020.","title":"Diachronic embedding for temporal knowledge graph completion","authors":"Rishab Goel, Seyed Mehran Kazemi, Marcus Brubaker, Pascal Poupart","year":"2020","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Han et al., 2021a] Zhen Han, Peng Chen, Yunpu Ma, and Volker Tresp. Explainable subgraph reasoning for fore- casting on temporal knowledge graphs. In ICLR, pages 1-24, 2021.","title":"Explainable subgraph reasoning for forecasting on temporal knowledge graphs","authors":"Han","year":"2021","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Han et al., 2021b] Zhen Han, Zifeng Ding, Yunpu Ma, Yu- jia Gu, and Volker Tresp. Learning neural ordinary equa- tions for forecasting future links on temporal knowledge graphs. In EMNLP, pages 8352-8364, 2021.","title":"Learning neural ordinary equations for forecasting future links on temporal knowledge graphs","authors":"Han","year":"2021","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Jiang et al., 2016] Tingsong Jiang, Tianyu Liu, Tao Ge, Lei Sha, Baobao Chang, Sujian Li, and Zhifang Sui. Towards time-aware knowledge graph completion. In COLING, pages 1715-1724, 2016.","title":"Towards time-aware knowledge graph completion","authors":"Jiang","year":"2016","venue":"COLING","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Jin et al., 2020] Woojeong Jin, Meng Qu, Xisen Jin, and Xiang Ren. Recurrent event network: Autoregressive structure inference over temporal knowledge graphs. In EMNLP, pages 6669-6683, 2020.","title":"Recurrent event network: Autoregressive structure inference over temporal knowledge graphs","authors":"Jin","year":"2020","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kazemi et al., 2019] Seyed Mehran Kazemi, Rishab Goel, Sepehr Eghbali, Janahan Ramanan, Jaspreet Sahota, San- jay Thakur, Stella Wu, Cathal Smyth, Pascal Poupart, and Marcus Brubaker. Time2vec: Learning a vector represen- tation of time. arXiv preprint arXiv:1907.05321, 2019.","title":"Time2vec: Learning a vector representation of time","authors":"Rishab Seyed Mehran Kazemi, Sepehr Goel, Janahan Eghbali, Jaspreet Ramanan, Sanjay Sahota, Stella Thakur, Cathal Wu, Pascal Smyth, Marcus Poupart, Brubaker","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Leblay and Chekol, 2018] Julien Leblay and Melisachew Wudage Chekol. Deriving validity time in knowledge graph. In WWW, pages 1771-1776, 2018.","title":"Deriving validity time in knowledge graph","authors":"Julien Leblay, Melisachew Wudage Chekol","year":"2018","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Li et al., 2021a] Zixuan Li, Xiaolong Jin, Saiping Guan, Wei Li, Jiafeng Guo, Yuanzhuo Wang, and Xueqi Cheng. Search from history and reason for future: Two-stage rea- soning on temporal knowledge graphs. In ACL, pages 4732-4743, 2021.","title":"Search from history and reason for future: Two-stage reasoning on temporal knowledge graphs","authors":"Li","year":"2021","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li et al., 2021b] Zixuan Li, Xiaolong Jin, Wei Li, Saiping Guan, Jiafeng Guo, Huawei Shen, Yuanzhuo Wang, and Xueqi Cheng. Temporal knowledge graph reasoning based on evolutional representation learning. In SIGIR, pages 408-417, 2021.","title":"Temporal knowledge graph reasoning based on evolutional representation learning","authors":"Li","year":"2021","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Ma et al., 2019] Yunpu Ma, Volker Tresp, and Erik A. Daxberger. Embedding models for episodic knowledge graphs. J. Web Semant., 59:100490, 2019.","title":"Embedding models for episodic knowledge graphs","authors":"Ma","year":"2019","venue":"J. Web Semant","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Mahdisoltani et al., 2015] Farzaneh Mahdisoltani, Joanna Biega, and Fabian M. Suchanek. Yago3: A knowledge base from multilingual wikipedias. In CIDR, pages 1-11, 2015.","title":"Yago3: A knowledge base from multilingual wikipedias","authors":"Farzaneh Mahdisoltani, Joanna Biega, Fabian M Suchanek","year":"2015","venue":"CIDR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Sadeghian et al., 2021] Ali Sadeghian, Mohammadreza Ar- mandpour, Anthony Colas, and Daisy Zhe Wang. Chronor: Rotation based temporal knowledge graph embedding. In AAAI, pages 6471-6479, 2021.","title":"Chronor: Rotation based temporal knowledge graph embedding","authors":"Ali Sadeghian, Mohammadreza Armandpour, Anthony Colas, Daisy Zhe Wang","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Schlesinger, 1999] Arthur M Schlesinger. The cycles of American history. Houghton Mifflin Harcourt, 1999.","title":"The cycles of American history","authors":"M Arthur, Schlesinger","year":"1999","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Seo et al., 2018] Youngjoo Seo, Michaël Defferrard, Pierre Vandergheynst, and Xavier Bresson. Structured sequence modeling with graph convolutional recurrent networks. In ICONIP, pages 362-373, 2018.","title":"Structured sequence modeling with graph convolutional recurrent networks","authors":"Seo","year":"2018","venue":"ICONIP","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Shang et al., 2019] Chao Shang, Yun Tang, Jing Huang, Jinbo Bi, Xiaodong He, and Bowen Zhou. End-to- end structure-aware convolutional networks for knowledge base completion. In AAAI, pages 3060-3067, 2019.","title":"End-toend structure-aware convolutional networks for knowledge base completion","authors":"Chao Shang, Yun Tang, Jing Huang, Jinbo Bi, Xiaodong He, Bowen Zhou","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Sun et al., 2021] Haohai Sun, Jialun Zhong, Yunpu Ma, Zhen Han, and Kun He. Timetraveler: Reinforcement learning for temporal knowledge graph forecasting. In EMNLP, pages 8306-8319, 2021.","title":"Timetraveler: Reinforcement learning for temporal knowledge graph forecasting","authors":"Sun","year":"2021","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Trivedi et al., 2017] Rakshit Trivedi, Hanjun Dai, Yichen Wang, and Le Song. Know-evolve: Deep temporal rea- soning for dynamic knowledge graphs. In ICML, pages 3462-3471, 2017.","title":"Know-evolve: Deep temporal reasoning for dynamic knowledge graphs","authors":"Rakshit Trivedi, Hanjun Dai, Yichen Wang, Le Song","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Trivedi et al., 2019] Rakshit Trivedi, Mehrdad Farajtabar, Prasenjeet Biswal, and Hongyuan Zha. Dyrep: Learning representations over dynamic graphs. In ICLR, pages 1- 25, 2019.","title":"Dyrep: Learning representations over dynamic graphs","authors":"Rakshit Trivedi, Mehrdad Farajtabar, Prasenjeet Biswal, Hongyuan Zha","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Trompf, 1979] Garry Winston Trompf. The idea of histor- ical recurrence in Western thought: From antiquity to the Reformation. Univ of California Press, 1979.","title":"The idea of historical recurrence in Western thought: From antiquity to the Reformation","authors":"Garry Winston, Trompf","year":"1979","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NeurIPS, pages 5998-6008, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, Illia Polosukhin","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wu et al., 2020] Jiapeng Wu, Meng Cao, Jackie Chi Kit Cheung, and William L. Hamilton. Temp: Temporal mes- sage passing for temporal knowledge graph completion. In EMNLP, pages 5730-5746, 2020.","title":"Temp: Temporal message passing for temporal knowledge graph completion","authors":"Wu","year":"2020","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhu et al., 2021] Cunchao Zhu, Muhao Chen, Changjun Fan, Guangquan Cheng, and Yan Zhang. Learning from history: modeling temporal knowledge graphs with se- quential copy-generation networks. In AAAI, pages 4732- 4740, 2021.","title":"Learning from history: modeling temporal knowledge graphs with sequential copy-generation networks","authors":"Zhu","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}